A5100704196- Hand Gesture Recognition Systems
- Video Surveillance and Tracking Methods
- Acute Ischemic Stroke Management
- Brain Tumor Detection and Classification
- Supercapacitor Materials and Fabrication
- Advanced Neural Network Applications
- Human Pose and Action Recognition
- Advanced Battery Materials and Technologies
- Advancements in Battery Materials
- AI in cancer detection
- Medical Imaging and Analysis
- Gait Recognition and Analysis
- Dental Radiography and Imaging
- Adipose Tissue and Metabolism
- Advanced Vision and Imaging
- Adipokines, Inflammation, and Metabolic Diseases
- Augmented Reality Applications
- Chemokine receptors and signaling
- MRI in cancer diagnosis
- Cancer, Hypoxia, and Metabolism
- Liver physiology and pathology
- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Digital Imaging for Blood Diseases
- Teleoperation and Haptic Systems
Korea University
2014-2021
University of Ulsan
2019-2020
Asan Medical Center
2018-2020
Ulsan College
2019-2020
Pohang University of Science and Technology
2014
Objective: To develop algorithms using convolutional neural networks (CNNs) for automatic segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) and compare them with conventional algorithms, including a thresholding-based segmentation.Materials Methods: Between September 2005 August 2015, 429 patients presenting cerebral ischemia (training:validation:test set = 246:89:94) were retrospectively enrolled in this study, which was performed under Institutional Review Board...
Abstract Pathologic diagnoses mainly depend on visual scoring by pathologists, a process that can be time-consuming, laborious, and susceptible to inter- and/or intra-observer variations. This study proposes novel method enhance pathologic of renal allograft rejection. A fully automated system using convolutional neural network (CNN) was developed identify regions interest (ROIs) detect C4d positive negative peritubular capillaries (PTCs) in giga-pixel immunostained slides. The performance...
This study introduces a simple and eco-friendly synthetic strategy for yolk-shell nanospheres that consist of manganese selenide yolks carbon shells (MnSe@C) by reacting salt impregnated in the porous hollow (HCNS) with H2O vapor. First, dissolved ethanol was into spacious pores HCNS capillary force. Then, heat treatment powder presence triggered nucleation crystal growth hydroxide, resulting formation whose central voids are filled multiple nanoparticles. Subsequent selenization yielded...
The problem of viewpoint variations is a challenging issue in vision-based human action recognition. With the richer information provided by three-dimensional (3-D) point clouds thanks to advent 3-D depth cameras, we can effectively analyze spatial actions. In this paper, propose volumetric feature representation (VSFR) that measures density for view-invariant recognition from sequence images. Using VSFR, construct self-similarity matrix (SSM) graphically represent temporal sequence. To...
Ischemic stroke, a common disease in the elderly, can cause long-term disability and death. Quantitative measurement of brain ischemic lesions at acute stage is vital for accurate diagnosis treatment decisions stroke patients. Currently, manual segmentation time-consuming, it difficult to extract potentially quantifiable information. These limitations be overcome via deep learning, which has recently become popular method segment MRI. Fully automatic methods using learning quantitatively...
The problem of viewpoint changes is an important issue in the study human action recognition. In this paper, we propose use spatial features a spatiotemporal self-similarity matrix (SSM) based on recognition that robust from depth sequences. represent discriminative density 3D point clouds grid. We construct SSM for change along with frames. To obtain SSM, compute Euclidean distance each feature between two represents similarity changes. Our proposed method and various length sequence. This...
Although molecular targeting therapy is an attractive treatment for cancer, resistance eventually develops in most cases. Here, we evaluated chemotherapeutic efficacy on non-small cell lung cancer (NSCLC) with acquired to epidermal growth factor receptor inhibitors mechanistically.Antitumor effects of taxotere were using multiple models, including xenograft, and patient-derived models developed from adenocarcinoma patients. Protein expressions analyzed after drug treatment.Taxotere inhibited...